Towards efficient post-training quantization of pre-trained language models

H Bai, L Hou, L Shang, X Jiang… - Advances in neural …, 2022 - proceedings.neurips.cc
Network quantization has gained increasing attention with the rapid growth of large pre-
trained language models~(PLMs). However, most existing quantization methods for PLMs …

RUL prediction of wind turbine gearbox bearings based on self-calibration temporal convolutional network

K He, Z Su, X Tian, H Yu, M Luo - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
The prediction of the remaining useful life (RUL) of wind turbine gearbox bearings is critical
to avoid catastrophic accidents and minimize downtime. Temporal convolutional network …

TWD-SFNN: Three-way decisions with a single hidden layer feedforward neural network

S Cheng, Y Wu, Y Li, F Yao, F Min - Information Sciences, 2021 - Elsevier
Neural networks have a strong self-learning ability and a wide range of applications. The
current neural network models mainly determine the number of hidden layer nodes using …

Model compression of deep neural network architectures for visual pattern recognition: Current status and future directions

S Bhalgaonkar, M Munot - Computers and Electrical Engineering, 2024 - Elsevier
Abstract Visual Pattern Recognition Networks (VPRNs) are widely used in various visual
data based applications such as computer vision and edge AI. VPRNs help to enhance a …

Hrel: Filter pruning based on high relevance between activation maps and class labels

CH Sarvani, M Ghorai, SR Dubey, SHS Basha - Neural Networks, 2022 - Elsevier
This paper proposes an Information Bottleneck theory based filter pruning method that uses
a statistical measure called Mutual Information (MI). The MI between filters and class labels …

Few shot network compression via cross distillation

H Bai, J Wu, I King, M Lyu - Proceedings of the AAAI Conference on …, 2020 - aaai.org
Abstract Model compression has been widely adopted to obtain light-weighted deep neural
networks. Most prevalent methods, however, require fine-tuning with sufficient training data …

A novel spatiotemporal prediction approach based on graph convolution neural networks and long short-term memory for money laundering fraud

P **a, Z Ni, H **ao, X Zhu, P Peng - Arabian Journal for Science and …, 2022 - Springer
Money laundering is an act of criminals attempting to cover up the nature and source of their
illegal gains. Large-scale money laundering has a great harm to a country's economy …

Optimization of the structural complexity of artificial neural network for hardware-driven neuromorphic computing application

K Udaya Mohanan, S Cho, BG Park - Applied Intelligence, 2023 - Springer
This work focuses on the optimization of the structural complexity of a single-layer
feedforward neural network (SLFN) for neuromorphic hardware implementation. The …

Stage-wise magnitude-based pruning for recurrent neural networks

G Li, P Yang, C Qian, R Hong… - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
A recurrent neural network (RNN) has shown powerful performance in tackling various
natural language processing (NLP) tasks, resulting in numerous powerful models containing …

DART: Domain-adversarial residual-transfer networks for unsupervised cross-domain image classification

X Fang, H Bai, Z Guo, B Shen, S Hoi, Z Xu - Neural Networks, 2020 - Elsevier
The accuracy of deep learning (eg, convolutional neural networks) for an image
classification task critically relies on the amount of labeled training data. Aiming to solve an …